mlsanityData to 7 Oct 2026

EVAF: A Test-Retest Protocol for Selective Parametric Consolidation

arXiv 2606.29916 ↗First posted 29 Jun 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Long-running language agents need mechanisms for deciding which experiences should persist after the working context is gone. Retrieval systems can reinsert past text, but they do not by themselves show that an experience has been selectively consolidated into the model's own behavior. We introduce EVAF, an Echo-Valence Attractor Field mechanism for gated LoRA consolidation, and a test-retest protocol for measuring selective parametric consolidation under controlled interference. Across GPT-2 and TinyLlama, EVAF preferentially consolidates high-valence, high-surprise experiences while preserving retrieval-accessible factual memory through a complementary routed memory path. Test-retest measurements show stronger post-interference behavioral persistence than frozen, retrieval-only, and ungated continual-update baselines, while keeping parameter drift and cross-persona contamination low. The results support a separation between memory access and memory depth: retrieving a fact and internalizing an experience are distinct computational operations.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 43 references that are in the map. First posted on arXiv 29 Jun 2026.

Builds on

29 of 43 references.

References · 29

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  4. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  5. 2016Progressive Neural Networkscited by 1,332
  6. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  7. 2018Experience Replay for Continual Learningcited by 1,074
  8. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  9. 2022Toy Models of Superpositioncited by 928
  10. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
  11. 2023The Linear Representation Hypothesis and the Geometry of Large Language Modelscited by 679
  12. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 656
17 more
  1. 2021Editing Factual Knowledge in Language Modelscited by 548
  2. 2022Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Spacecited by 522
  3. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memorycited by 372
  4. 2023Adapting Language Models to Compress Contextscited by 350
  5. 2023Language Models Represent Space and Timecited by 306
  6. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 273
  7. 2022Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptorscited by 267
  8. 2022Memorizing Transformerscited by 219
  9. 2023Progressive Prompts: Continual Learning for Language Modelscited by 195
  10. 2023In-context Autoencoder for Context Compression in a Large Language Modelcited by 190
  11. 2023Linearity of Relation Decoding in Transformer Language Modelscited by 190
  12. 2019Meta-Learning Representations for Continual Learningcited by 189
  13. 2017FearNet: Brain-Inspired Model for Incremental Learningcited by 177
  14. 2024Larimar: Large Language Models with Episodic Memory Controlcited by 53
  15. 2025Beyond a Million Tokens: Benchmarking and Enhancing Long-Term Memory in LLMscited by 52
  16. 2023Task Arithmetic with LoRA for Continual Learningcited by 31
  17. 2017Fast-Slow Recurrent Neural Networkscited by 12

Built on by

Not cited yet.